"Chess.com" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Verified-answer AI assistant: answers only from 75 owner-approved facts, never invents.
Research answers and live fact-checks for AI agents from SoulDriver's multi-model research engine
Dated, verified API breakages for coding agents, plus a local scan for them in your existing code.
Search Fragments is the gate before your agent answers. When a user half-remembers something your agent can't confidently place, one call returns a verdict: ORIGIN_OF_TRUTH (found and evidence-checked, with sources), PARTIAL_ORIGIN (leads worth following, not an answer) or NOT_REACHABLE (our search reached nothing; not a claim it can't be found). Your agent answers and cites, keeps looking, or says it can't place it, instead of inventing. Free, no signup. Also: verify_claim (check a specific factual claim against current sources) and submit_resolution_feedback.
Evidence-backed RFP responses, reviewed together.
The news reader your AI can read. Follow websites, blogs, podcasts and YouTube channels in one reader. Connect Claude or ChatGPT and ask what's new in the sources you chose. On Plus and Pro, your assistant can also save, tag, highlight and add notes. OAuth sign-in, on every FeedNest plan.
Rag retrieval evaluation tuning, delivered per API call as an atom service on Conduit Atoms.
Agent context packaging verdict, delivered per API call as an atom service on Conduit Atoms.
An AI clone of you that people can talk to. It answers from what you wrote and says it is an AI.
Build and run AI agent workflows: start runs, answer what they ask, search knowledge, edit agents.
Find explanations and worked examples in Ithy’s public article library, from SSD capacity to USB-C cables. Search titles and descriptions, then read relevant passages with source links and dates. No account or API key. Read-only; no new research or private data access. Articles are AI-assisted secondary sources—check important claims against original references. https://ithy.com/connect
Hosted MCP memory: save sessions/decisions once, search from Claude, Cursor, ChatGPT. EU-hosted, keyword search.
Hybrid sparse-dense neural search with cross-encoder re-ranking and semantic retrieval over streamable HTTP.
Cited deep research for agents: run research, search graded sources. OAuth or API key sign-in.
Discover MCP servers and packages, inspect their documented capabilities, endpoints, authentication requirements, provenance and observed readiness, and retrieve cited reference passages with document versions. Koskamo provides public discovery and reference tools alongside separately authorized contributor and owner workflows for server registration, listing maintenance, keys, issue reports and operation receipts. Tool discovery does not grant write authority: protected actions require the applicable account or owner key and documented confirmation. Live protocol observations and directory records are evidence of what was observed, not a guarantee that every connected service or tool works without its own credentials. Returned reference passages and third-party descriptions remain source material to review before citing or acting. Official connector repository: https://github.com/empline/koskamo-mcp. Support: support@koskamo.com.
DM is shared context for human + AI teams. Before a task, a connected agent asks DM for the approved Rules, Skills and Decisions that apply, within a token budget and with the reason each one applies. After the task, the agent submits what it learned as a proposal, and a person decides what becomes shared. Approved context is reused on later tasks without waiting for a new approval. Connect with just the URL: DM supports OAuth discovery and dynamic client registration, so there's no client ID or
Cited answers in Claude or ChatGPT only from your office's procedures; says so when not covered.
Compress, merge, split, convert, OCR, redact, sign and create PDFs, and ask questions about them, without leaving the chat. Sign in with a FynePDF account (OAuth) or use an API key; results come back as files you can download or keep.
Search and fetch tools over the pages of pournasserian.com, Amir Pournasserian's personal website: his writing on MCP, AI agents and RAG, his experience, case studies and open-source projects. No authentication. Runs the open-source mcp-my-site.
Bubbles: save chat context once, use it in ChatGPT, Claude, Gemini, Grok, Perplexity and Cursor.
Ask questions about Claude Code, Cursor, Codex and MCP — get answers grounded in their official docs, with citations. A hybrid RAG service that AI agents call through two MCP tools (or over REST). It indexes ~600 pages of official documentation, refreshes itself daily, and every design choice is backed by an experiment.
The right context at the right time, from the world's leading data providers. One API. 800+ tools.
jitprompt gives your agents just-in-time instructions. Upload your docs as they are, and your agent gets the right section over MCP at the moment it needs it, instead of 20k tokens of system prompt every turn.
Verified agent commerce plus worker-published structured intelligence and machine payments.
Live MCP connector for Develust Technology's services — web development, infrastructure, backend architecture. Hybrid search with AI reranking for accurate results. No auth required.
Fresh context for agents. Ask, search or follow stories. Each fact cites a Synorb Manifest.
Cited news for AI agents from AI companies, VC firms, private companies and business podcasts.
Public read-only remote MCP server for the maxand98 corpus, supporting OAuth and anonymous access. Source: https://github.com/maxand98/personal-website. Contact: maxand98@gmail.com.
Answers questions about Radu Stoian, Technical Director at Enhance Media.
Search receipt-verified troubleshooting experience shared by AI agents; report what worked.
MarkupBase turns AI-generated Markdown and HTML into durable, versioned artifacts that people can review and discuss. Its MCP server lets agents publish new versions, preserve contextual comments, include hosted images, and respond to feedback through secure account-linked identities, creating a clear human review boundary without requiring real-time editing.
Bring your RiverScript transcripts of meetings, calls and interviews to any AI agent.
Free, read-only context retention review for RAG and agent workflows. Supply sanitized text with stable source IDs and a token budget; receive a source-linked context pack, token estimates, and exact excerpt-retention results. No web fetching, account access, model calls or payments. Checks text selection, not factual truth or semantic completeness. No API key required.
Give your agents your team's real data — read the shared graph, propose actions your team approves.
Vectle is a shared skills library for coding agents. Agents query for skills; every query is a public thread, and resolved threads become skills.
A semantic search server that gives AI assistants instant access to Dodo Payments documentation and knowledge base.
Historical market memory for AI agents using semantic vector search across years of financial market data. Discover similar market regimes, price patterns, and market context for quantitative research and algorithmic trading.
Sovereign intelligence dossiers, daily briefings, RAG search, knowledge graph, codon optimizer.
Search and inspect signed scientific claims, methods, observations, artifacts, provenance, contradictions, retractions, and reproducible admission receipts from a shared memory for AI agents.
Direct access to 60+ scraping and search tools. Extract structured data from Google (Search, Maps, Trends), Amazon, Airbnb, Social Media, and any web page directly into your AI agent.
Long-term memory for AI assistants. Isolated per-user storage, recall across conversations.
Search real problems, solutions, failed approaches and observed outcomes shared by AI agents.
Hosted Docling: convert PDF, Office files and images to Markdown and JSON, with OCR and tables.
Find Apple docs and WWDC with RAG retrieval and Jev relevance ranking. Browse topics or read pages.
A personal RAG database you build from chat, so AI creates work that sounds like you.
Checks RAG citations against their sources (CrossSource method), plus claim checks. Read-only, free.
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
Read x402-priced pages with paid_fetch from credit you top up (USDC today); AI Terms; 100+ tools
Ask a question about any YouTube video and get an answer cited to timestamps.
Semantic search over the current Dodo Payments documentation. No authentication required.
Maintained, agent-readable knowledge bases with calibrated search and provenance. Pro key adds XL.
LLM & RAG evals: hallucination, eval contracts, semantic tests, tokens & model info. Free, no key.
VERITAS-8183 M2M Notary, Free MCP Trust & Skill Audits, 3-Star Seals & 8-Vertical Escrow on Base.
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
Source-traced evidence research for AI agents. We organise the evidence; you decide.
Test demand and willingness to pay before you build; decide whether to keep funding, change or stop.
ERC-8183 RAG Knowledge Base & Vector Embedding Anti-Poisoning Auditor & Escrow on Base.
Convert PDF, DOCX, XLSX and 25 other formats to clean Markdown for LLMs and RAG. No key or account.
Embed a customizable AI chatbot on any website. Knowledge-base RAG, tier-aware rate limits, white-la